2 papers
cs.CL2024
Safe-Embed: Unveiling the Safety-Critical Knowledge of Sentence Encoders
Jinseok Kim, Jaewon Jung, Sangyeop Kim +2
Despite the impressive capabilities of Large Language Models (LLMs) in various tasks, their vulnerability to unsafe prompts remains a critical issue. These prompts can lead LLMs to…
cs.AR2024
Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System
Hongsun Jang, Jaeyong Song, Jaewon Jung +3
The recent huge advance of Large Language Models (LLMs) is mainly driven by the increase in the number of parameters. This has led to substantial memory capacity requirements, nece…